Robust Speech Recognition via Large-Scale Weak Supervision

The official Meta Llama 3 GitHub site

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.

Reference implementations of MLPerf™ training benchmarks

Complete YOLO v3 TensorFlow implementation. Support training on your own dataset.

StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text

Tools for handling speech data in machine learning projects.

Inference code for the paper "Spirit-LM Interleaved Spoken and Written Language Model".

LLM Transparency Tool (LLM-TT), an open-source interactive toolkit for analyzing internal workings of Transformer-based language models. *Check out demo at* https://huggingface.co/spaces/facebook/l…

Python re-implementation of the (constrained) spectral clustering algorithms used in Google's speaker diarization papers.

Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch

A fast and lightweight python-based CTC beam search decoder for speech recognition.

Efficient LLM Inference over Long Sequences

NeMo text processing for ASR and TTS

LLM KV cache compression made easy

[ASRU 2021] Efficient Conformer: Progressive Downsampling and Grouped Attention for Automatic Speech Recognition

A toolkit for processing speech data and creating speech datasets

Python package for combining diarization system outputs.

Official repository of NeXt-TDNN for speaker verification

Tensorflow QANet with ELMo

SLT 2024 Challenge: Post-ASR-Speaker-Tagging

Supervised/Unsupervised Alignment of Clear/Anonymized X-Vector with Procrustes/Wasserstein Procrustes

Tokenizer for Armenian Language

[Yerevan 24] Authorship Style Transfer with Policy Optimization